Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    questions that start with "Which."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ald
    -0.16
    egg
    -0.15
    ental
    -0.14
    loff
    -0.14
    ran
    -0.14
    sson
    -0.14
    ict
    -0.14
    alt
    -0.14
    uto
    -0.14
    rette
    -0.14
    POSITIVE LOGITS
    soever
    0.30
     ones
    0.24
     именно
    0.23
    -ever
    0.23
     direction
    0.22
     Wich
    0.21
    /how
    0.21
     Ñģаме
    0.18
     version
    0.18
     among
    0.18
    Act Density 0.038%

    No Known Activations